Abstract
A brief overview of the Hopfield Neural Network is presented to emphasize the benefits of implementing neural circuits in actual hardware. The limitations associated with the standard Hopfield Network are then discussed, and the need for a better architecture is highlighted. A neural architecture in which the nature of feedback is non-linear, as opposed to the linear feedback in Hopfield Networks, is explained. It is further demonstrated that such non-linear feedback neural networks are capable of providing better solutions to combinatorial problems like graph colouring and sorting. The chapter ends with an overview of pertinent technical literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rahman, S.A., Jayadeva, C., Dutta Roy, S.C.: Neural network approach to graph colouring. Electron. Lett. 35(14), 1173–1175 (1999)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79(8), 2554–2558 (1982)
Hopfield, J.J., Tank, D.W.: “Neural” computation of decisions in optimization problems. Biol. Cybernet. 52, 141–152 (1985)
Tank, D., Hopfield, J.: Simple ‘neural’ optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans. Circ. Syst. 33(5), 533–541 (1986)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81(10), 3088–3092 (1984)
Vidyasagar, M.: Location and stability of the high-gain equilibria of nonlinear neural networks. IEEE Trans. Neural Netw. 4(4), 660–672 (1993)
Wilson, G.V., Pawley, G.S.: On the stability of the travelling salesman problem algorithm of hopfield and tank. Biol. Cybern. 58(1), 63–70 (1988)
Kamgar-Parsi, B., Kamgar-Parsi, B.: Dynamical stability and parameter selection in neural optimization. In Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 566–571, Baltimore, USA (1992)
Aiyer, S.V.B., Niranjan, M., Fallside, F.: A theoretical investigation into the performance of the hopfield model. IEEE Trans. Neural Netw. 1(2), 204–215 (1990)
Gee, A.H.: Problem Solving with Optimization Networks. PhD thesis, University of Cambridge, UK (1993)
Van den Bout, D.E., Miller, T.K.: A traveling salesman objective function that works. In: Proceedings of IEEE International Conference on Neural Networks, pp. 299–303, San Diego, USA (1988)
Nonaka, H., Kobayashi, Y.: Sub-optimal solution screening in optimization by neural networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 606–611, Baltimore, USA (1992)
Foo, Y.P.S., Szu, H.: Solving large-scale optimization problems by divide-and-conquer neural networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 507–511, Washington, DC, USA (1989)
Lo, J.T.-H.: A new approach to global optimization and its applications to neural networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 600–605, Baltimore, USA (1992)
Amartur, S.C., Piraino, D., Takefuji, Y.: Optimization neural networks for the segmentation of magnetic resonance images. IEEE Trans. Med. Imaging 11(2), 215–220 (1992)
Chen, L., Aihara, K.: Chaotic simulated annealing by a neural network model with transient chaos. Neural Netw. 8(6), 915–930 (1995)
Arabas, J., Kozdrowski, S.: Applying an evolutionary algorithm to telecommunication network design. IEEE Trans. Evol. Comput. 5(4), 309–322 (2001)
Rahman, S.A.: A nonlinear synapse neural network and its applications. PhD thesis, Department of Electrical Engineering, Indian Institute of Technology, Delhi, India (2007)
Jayadeva, Rahman, S.A.: A neural network with O(N) neurons for ranking N numbers in O(1/N) time. IEEE Trans. Circ. Syst. I: Regular Papers 51(10):2044–2051 (2004)
Jensen, T.R., Toft, B.: Graph Coloring Problems. John Wiley & Sons, New York (1994)
Gassen, D.W., Carothers, J.D.: Graph color minimization using neural networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 1541–1544, Nagoya, Japan (1993)
El-Fishawy, N.A., Hadhood, M.M., Elnoubi, S., EL-Sersy, W.: A modified hopfield neural network algorithm for cellular radio channel assignment. In: Proceedings of TENCON, pp. 213–216, Kuala Lumpur, Malaysia (2000)
LaPaugh, A.S.: VLSI Layout algorithms. Chapman & Hall/CRC, Boca Raton (2010)
Yue, T.-W., Lee, Z. Z.: A Q’tron neural-network approach to solve the graph coloring problems. In: Proceedings of 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI), pp. 19–23, Paris, France (2007)
Graph Coloring Instances. http://mat.gsia.cmu.edu/COLOR/instances.html. Accessed 10 February 2012
Gustafson, J.L.: The quest for linear equation solvers and the invention of electronic digital computing. In: Proceedings of IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing (JVA’06), pp. 10–16, Sofia (2006)
Yong, L.L.: Jiu Zhang Suanshu (nine chapters on the mathematical art): an overview. Arch. Hist. Exact Sci. 47(1), 1–51 (1994)
Kleiner, I.: History of Linear Algebra, pp. 79–89. Birkhauser, Basel (2007)
Peters, G., Wilkinson, J.H., Martin, R.S.: Iterative refinement of the solution of a positive definite system of equations. Numer. Math. 8, 203–216 (1966)
White, S.: A brief history of computing—complete timeline. http://trillian.randomstuff.org.uk/stephen/history/timeline.html. Accessed 30 October 2012
Kung, S.: VLSI array processors. IEEE ASSP Mag. 2(3), 4–22 (1985)
Wilburn, V.C., Ko, H.-L., Alexander, W.E.: An algorithm and architecture for the parallel solution of systems of linear equations. In: Proceedings of IEEE Fifteenth Annual International Phoenix Conference on Computer and Communications, pp. 392–398, Scottsdale, USA, March 1996
Wilbur, J.B.: The mechanical solution of simultaneous equations. J. Franklin Inst. 222, 715–724 (1936)
Walker, R.M.: An analogue computer for the solution of linear simultaneous equations. Proc. IRE Waves Electrons Section 37(12), 1467–1473 (1949)
Ackerman, S.: Precise solutions of linear simultaneous equations using a low cost analog. Rev. Sci. Instrum. 22(10), 746–748 (1951)
Many, A., Oppenheim, U., Amitsur, S.: An electrical computer for the solution of linear simultaneous equations. Rev. Sci. Instrum. 24(2), 112–116 (1953)
Mitra, S.K.: Electrical analog computing machine for solving linear equations and related problems. Rev. Sci. Instrum. 26(5), 453–457 (1955)
Hutchinson, J., Koch, C., Luo, J., Mead, C.: Computing motion using analog and binary resistive networks. Computer 21(3), 52–63 (1988)
Jang, J., Lee, S., Shin, S.: An Optimization Network for Matrix Inversion, pp. 397–401. American Institute of Physics, New York (1988)
Chakraborty, K., Mehrotra, K., Mohan, C.K., Ranka, S.: An optimization network for solving a set of simultaneous linear equations. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), pp. 516–521, Baltimore, USA, June 1992
Wang, J.: Electronic realization of recurrent neural network for solving simultaneous linear equations. Electron. Lett. 28(5), 493–495 (1992)
Cichocki, A., Unbehauen, R.: Neural networks for solving systems of linear equations and related problems. IEEE Trans. Circ. Syst. I: Fundam. Theory Appl. 39(2), 124–138 (1992)
Cichocki, A., Unbehauen, R.: Neural networks for solving systems of linear equations. Part ii. Minimax and least absolute value problems. IEEE Trans. Circ. Syst. II: Analog Digital Signal Processing 39(9), 619–633 (1992)
Wang, J., Li, H.: Solving simultaneous linear equations using recurrent neural networks. Inf. Sci. Intell. Syst. 76(3), 255–277 (1994)
Zhang, K., Ganis, G., Sereno, M.I.: Anti-hebbian synapses as a linear equation solver. In: Proceedings of International Conference on Neural Networks, pp. 387–389, Houston, TX, USA, June 1997
Xia, Y., Wang, J., Hung, D.L.: Recurrent neural networks for solving linear inequalities and equations. IEEE Trans. Circ. Syst. I: Fundam. Theory Appl. 46(4), 452–462 (1999)
Jiang, D.: Analog computing for real-time solution of time-varying linear equations. In: Proceedings of International Conference on Communications, Circuits and Systems (ICCCAS), pp. 1367–1371, June 2004
Wang, X., Ziavras, S.G.: Parallel direct solution of linear equations on FPGA-based machines. In: Proceedings of International Parallel and Distributed Processing Symposium (IPDPS’03), pp. 113–120, Nice, France, April 2003
Kreyszig, E.: Advanced Engineering Mathematics, 8th edn. Wiley-India (2006)
Kambo, N.S.: Mathematical Programming Techniques, revised edn. Affilated East-West Press Pvt Ltd., New Delhi (1991)
Anguita, D., Boni, A., Ridella, S.: A digital architecture for support vector machines: theory, algorithm, and FPGA implementation. IEEE Trans. Neural Netw. 14(5), 993–1009 (2003)
Cichocki, A., Unbehauen, R.: Neural Networks for Optimization and Signal Processing. Wiley, Chichester (1993)
Iqbal, K., Pai, Y.C.: Predicted region of stability for balance recovery: motion at the knee joint can improve termination of forward movement. J. Biomech. 13(12), 1619–1627 (2000)
Zhang, Y.: Towards piecewise-linear primal neural networks for optimization and redundant robotics. In: Proceedings of IEEE International Conference on Networking, Sensing and Control, pp. 374–379, Fort Lauderdale, Florida, USA (2006)
Zhang, Y., Leithead, W.E.: Exploiting hessian matrix and trust-region algorithm in hyperparameters estimation of gaussian process. Appl. Math. Comput. 171(2), 1264–1281 (2005)
Young, M.R.: A minimax portfolio selection rule with linear programming solution. Manage. Sci. 44(5), 673–683 (1988)
Bixby, R.E., Gregory, J.W., Lustig, I.J., Marsten, R.E., Shanno, D.F.: Very large-scale linear programming: a case study in combining interior point and simplex methods. Oper. Res. 40(5), 885–897 (1992)
Peidro, D., Mula, J., Jimenez, M., del Mar Botella, M.: A fuzzy linear programming based approach for tactical supply chain planning in an uncertainty environment. Eur. J. Oper. Res. 205(16), 65–80 (2010)
Chertkov, M., Stepanov, M.G.: An efficient pseudocodeword search algorithm for linear programming decoding of LDPC codes. IEEE Trans. Inf. Theory 54(4), 1514–1520 (2008)
ChvÃtal, V., Cook, W., Dantzig, G.B., Fulkerson, D.R., Johnson, S.M.: Solution of a Large-Scale Traveling-Salesman Problem, pp. 7–28. Springer, Berlin, (2010)
Atkociunas, J.: Quadratic programming for degenerate shakedown problems of bar structures. Mech. Res. Commun. 23(2), 195–206 (1996)
Bartlett, R.A., Wachter, A., Biegler, L.T.: Active set vs. interior point strategies for model predictive control. In: Proceedings of American Control Conference, pp. 4229–4233, Chicago, USA, June 2000
Maier, G., Munro, J.: Mathematical programming applications to engineering plastic analysis. Appl. Mech. Rev. 35, 1631–1643 (1982)
Nordebo, S., Zang, Z., Claesson, I.: A semi-infinite quadratic programming algorithm with applications to array pattern synthesis. IEEE Trans. Circ. Syst. II: Analog and Digital Signal Processing 48(3), 225–232 (2001)
Schonherr, S.: Quadratic programming in geometric optimization: theory, implementation, and applications. PhD thesis, Swiss Federal Institute of Technology, Zurich (2002)
Borguet, S., Leonard, O.: A quadratic programming framework for constrained and robust jet engine health monitoring. Progr. Propul. Phys. 1, 669–692 (2009)
Dembo, R.S., Tulowitzki, U.: Computing equilibria on large multicommodity networks: an application of truncated quadratic programming algorithms. Networks 18(4), 273–284 (1988)
Censor, Y., Elfving, T.: New methods for linear inequalities. Linear Algebra Appl. 42, 199–211 (1982)
Wen, U.-P., Lan, K.-M., Shih, H.-S.: A review of hopfield neural networks for solving mathematical programming problems. Eur. J. Oper. Res. 198(3), 675–687 (2009)
Kennedy, M.P., Chua, L.O.: Neural networks for nonlinear programming. IEEE Trans. Circ. Syst. 35(5), 554–562 (1988)
Rodriguez-Vazquez, A., Rueda, A., Huertas, J.L., Dominguez-Castro, R.: Switched-capacitor neural networks for linear programming. Electron. Lett. 24(8), 496–498 (1988)
Rodriguez-Vazquez, A., Dominguez-Castro, R., Rueda, A., Huertas, J.L., Sanchez-Sinencio, E.: Nonlinear switched capacitor ‘neural’ networks for optimization problems. IEEE Trans. Circ. Syst. 37(3), 384–398 (1990)
Lan, K.-M., Wen, U.-P., Shih, H.-S., Lee, E.S.: A hybrid neural network approach to bilevel programming problems. Appl. Math. Lett. 20(8), 880–884 (2007)
Maa, C.-Y., Shanblatt, M.A.: Linear and quadratic programming neural network analysis. IEEE Trans. Neural Netw. 3(4), 580–594 (1992)
Chong, E.K.P., Hui, S., Zak, S.H.: An analysis of a class of neural networks for solving linear programming problems. IEEE Trans. Autom. Control 44(11), 1995–2006 (1999)
Zhu, X., Zhang, S., Constantinides, A.G.: Lagrange neural networks for linear programming. J. Parallel Distrib. Comput. 14(3), 354–360 (1992)
Xia, Y., Wang, J.: Neural network for solving linear programming problems with bounded variables. IEEE Trans. Neural Netw. 6(2), 515–519 (1995)
Malek, A., Yari, A.: Primal-dual solution for the linear programming problems using neural networks. Appl. Math. Comput. 167(1), 198–211 (2005)
Ghasabi-Oskoei, H., Malek, A., Ahmadi, A.: Novel artificial neural network with simulation aspects for solving linear and quadratic programming problems. Comput. Math. Appl. 53(9), 1439–1454 (2007)
Wang, J.: Recurrent neural network for solving quadratic programming problems with equality constraints. Electron. Lett. 28(14), 1345–1347 (1992)
Forti, M., Tesi, A.: New conditions for global stability of neural networks with application to linear and quadratic programming problems. IEEE Trans. Circ. Syst. I: Fundam. Theory Appl. 42(7), 354–366 (1995)
Wu, X.-Y., Xia, Y.-S., Li, J., Chen, W.-K.: A high-performance neural network for solving linear and quadratic programming problems. IEEE Trans. Neural Netw. 7(3), 643–651 (1996)
Xia, Y.: A new neural network for solving linear and quadratic programming problems. IEEE Trans. Neural Netw. 7(6), 1544–1548 (1996)
Tao, Q., Cao, J., Sun, D.: A simple and high performance neural network for quadratic programming problems. Appl. Math. Comput. 124(2), 251–260 (2001)
Liu, Q., Wang, J.: A one-layer recurrent neural network with a discontinuous hard-limiting activation function for quadratic programming. IEEE Trans. Neural Netw. 19(4), 558–570 (2008)
Gould, N.I.M., Toint, P.L.: A quadratic programming bibliography. Technical report, RAL Numerical Analysis Group, March 2010
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2014 Springer India
About this chapter
Cite this chapter
Ansari, M.S. (2014). Background. In: Non-Linear Feedback Neural Networks. Studies in Computational Intelligence, vol 508. Springer, New Delhi. https://doi.org/10.1007/978-81-322-1563-9_2
Download citation
DOI: https://doi.org/10.1007/978-81-322-1563-9_2
Published:
Publisher Name: Springer, New Delhi
Print ISBN: 978-81-322-1562-2
Online ISBN: 978-81-322-1563-9
eBook Packages: EngineeringEngineering (R0)